CS-E4000 - Seminar in Computer Science D, 11.01.2021-30.04.2021

ASA: Use of GSMA consumer RSP protocol in the IoT domain and its security implication

Tutor: Abu Shohel Ahmed

• https://www.gsma.com/esim/wp-content/uploads/2020/06/SGP.22-v2.2.2.pdf

AP: Formal Verification of Cryptographic Protocols

Tutor: Aleksi Peltonen

Formal verification is a group of techniques based on applied mathematics. These methods can be divided into two categories: (1) deductive and (2) model-based verification. Deductive verification involves inferring the correctness of a system specification with axioms and proof rules. Model-based verification, on the other hand, involves using a model checker to create a state model of the system and performing exhaustive state exploration to prove or disprove properties of the protocol. When an error or goal state is reached, the model checker typically provides a trace leading to it from the initial state. Formal verification methods are often used to prove the reliability of commonly used protocols, such as TLS 1.3, and they have been used by companies such as Amazon and Facebook to eliminate bugs in large-scale services. In this topic the student will learn about verification of cryptographic protocols with a state-of-the-art verification tool and demonstrate how it can be used to analyse a cryptographic protocol. The choice of tool and protocol will be agreed upon with the supervisor.

References: 

• http://tamarin-prover.github.io/ 
• https://prosecco.gforge.inria.fr/personal/bblanche/proverif/
•  https://www.mcrl2.org/web/user_manual/index.html

AA: Causal reasoning in reinforcement learning

Tutor: Alexander Aushev

Can reinforcement learning agents learn performing and interpreting the experiments in the environment? Motivated by how human brains explore causal structures in the environment while doing a task, the field of causal reasoning in reinforcement learning tries to adapt this ability for agents. The necessity in causal reasoning naturally arises in biology, operational research, communications and, more generally, in all fields where the environment can be represented as a system of interconnected nodes. Recent developments in the field showed how inference of causal structures result in a more accurate and interpretable performance. For this topic you will review papers related to causal reasoning in reinforcement learning and focus on challenges, applications and state-of-the-art techniques of this field.

References:

• Discovering latent causes in reinforcement learning: https://thesnipermind.com/images/Studies-PDF-Format/GershmanNormanNiv15.pdf
• Gershman, Samuel J. "Reinforcement learning and causal models." The Oxford handbook of causal reasoning. Oxford University Press, 2017. 295 https://books.google.fi/books?hl=en&lr=&id=2qt0DgAAQBAJ&oi=fnd&pg=PA295&dq=causal+inference+in+reinforcement+learning&ots=azhyblbLVV&sig=hM5tQeK0fH8-yrOXpFesGSXRVc0&redir_esc=y#v=onepage&q=causal%20inference%20in%20reinforcement%20learning&f=false
  

AN: Auto time series forecasting for the regression problems

Tutor: Alexander Nikitin

• https://ai.googleblog.com/2020/12/using-automl-for-time-series-forecasting.html
• https://www.usenix.org/conference/opml20/presentation/huang 
•  https://towardsdatascience.com/time-series-forecasting-neuralprophet-vs-automl-fa4dfb2c3a9e

AYJ: WEB-based mobile augmented reality

Tutor: Antti Ylä-Jääski

Augmented reality running on mobile devices usually is based on Apps that are built from ARCore, ARKit, Unity, etc. Web-based AR (Web AR) implementation can provide a pervasive Mobile AR experience to users thanks to the many successful deployments of the Web as a lightweight and cross-platform service provisioning platform. Furthermore, the emergence of 5G mobile communication networks has the potential to enhance the communication efficiency of Mobile AR dense computing in the Web-based approach. This topic asks the student to make a survey of the challenges and opportunities for web-based mobile augmented reality. This work can be completed as a sole literature survey, however, there is also a possibility to make a small-scale web-based mobile augmented reality experimental part.

References:

• 2019 Proceedings of the IEEE 107(4):1-16 Web AR: A Promising Future for Mobile Augmented Reality - State of the Art, Challenges, and Insights https://ieeexplore.ieee.org/document/8643424 
•  2020 IEEE Transactions on Cloud computing Edge AR X5: An Edge-Assisted Multi-User Collaborative Framework for Mobile Web Augmented Reality in 5G and Beyond https://ieeexplore.ieee.org/abstract/document/9300168
•  Augmented reality for the web https://developers.google.com/web/updates/2018/06/ar-for-the-web
  

BL1: Adversarial machine learning defenses

Turtor: Blerta Lindqvist

Neural network classifiers are susceptible to attacks that cause misclassification. Many of the proposed defenses have been disputed, leaving only few standing.

References:

• https://nicholas.carlini.com/writing/2019/all-adversarial-example-papers.html
  

Bl2:Adversarial machine learning attacks

BGAT: Robustness and Privacy in Federated Learning

Tutor: Buse Gul Atli Tekgul

Federated learning is a distributed machine learning setting, where training is done on edge devices owned by clients and coordinated via a central server or a service provider [1,2]. Federated learning allows clients to store their own data locally; therefore, it does not compromise the privacy of clients’ data. Today companies like NVIDIA and Google has federated learning settings and clients (e.g., owner of cell-phone devices) both participate the training and get personalised apps without worrying about possible leakage of their sensitive datasets. Recent work has shown that, since the model is downloaded by clients participating to training, they can implement different adversarial attacks against federated learning models [3]. There have been attacks against the integrity: Poisoning attacks [5] aim to manipulate the model parameters such that its performance degrades completely or on some specific samples. Another well-known attack type is attacks against confidentiality: Malicious clients (or a malicious server) exploit the vulnerabilities of the learning algorithm in order to get information about other client's data [4]. In this seminar topic, the student(s) are expected to do a survey of attacks and defences related to the robustness and privacy of the federated learning.

References:

• [1] Bonawitz, Keith, et al. "Towards federated learning at scale: System design." arXiv preprint arXiv:1902.01046 (2019). 
  
• [2] McMahan, Brendan, et al. "Communication-efficient learning of deep networks from decentralized data." Artificial Intelligence and Statistics. PMLR, 2017. 
• [3] Kairouz, Peter, et al. "Advances and open problems in federated learning." arXiv preprint arXiv:1912.04977 (2019).
•  [4] Nasr, Milad, Reza Shokri, and Amir Houmansadr. "Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning." 2019 IEEE Symposium on Security and Privacy (SP). IEEE, 2019. 
• [5] Fang, Minghong, et al. "Local model poisoning attacks to Byzantine-robust federated learning." 29th {USENIX} Security Symposium ({USENIX} Security 20). 2020.

CY: Uncertainty Quantification in Neural ODE Models

Tutor: Cagatay Yildiz

References:

ER: Semantic description of policies for intelligent services in distributed environments

 Tutor: Edgar Ramos

Policies targeting how a device can be used or who is allowed to do what with the device and what kind of operations are allowed or should be enforced with the data are needed to manage IoT devices that run intelligence services. A high-level description of these policies can be provided to devices and translated to concrete policies that the device can understand (for example, read, write, id requirements, etc). One approach in this direction is the use of semantics descriptions to provide such policies using for example semantic constructions with a descriptive language. The IoT applications are inherently heterogeneous and their capacity to interpreter high-level policies is limited to their domain. Therefore domain of application should be also taken care in the definition and interpretation of such policies. 

References: 

• AWS idAM is quite an interesting implementation in this direction (https://docs.aws.amazon.com/IAM/latest/UserGuide/intro-structure.html) An article on policy semantics language description: Kagal L., Finin T., Joshi A. (2003) 
  
• A Policy Based Approach to Security for the Semantic Web. In: Fensel D., Sycara K., Mylopoulos J. (eds) The Semantic Web - ISWC 2003. ISWC 2003. Lecture Notes in Computer Science, vol 2870. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-39718-2_26
• Policy language from AWS : https://docs.aws.amazon.com/IAM/latest/UserGuide/iam-ug.pdf#reference_policies_grammar

GI: Foveated Video Quality Metrics

Tutor: Gazi Illahi

• 1.Lee, Sanghoon, Marios S. Pattichis, and Alan C. Bovik. "Foveated video quality assessment." IEEE Transactions on Multimedia 4, no. 1 (2002): 129-132. 
• 2. Jin, Yize, et al. "Study of 2D foveated video quality in virtual reality." Applications of Digital Image Processing XLIII. Vol. 11510. International Society for Optics and Photonics, 2020. 
• 3. S. Rimac-Drlje, G. Martinović and B. Zovko-Cihlar, "Foveation-based content Adaptive Structural Similarity index," 2011 18th International Conference on Systems, Signals and Image Processing, Sarajevo, 2011, pp. 1-4.
  

HD: TinyML as-a-Service - bringing Machine Learning inference to the deepest IoT edge

Tutor: Hiroshi Doyu

TinyML, as a concept, concerns the running of ML inference on Ultra Low-Power (ULP ~1mW) microcontrollers found on IoT devices. Yet today, various challenges still limit the effective execution of TinyML in the embedded IoT world. As both a concept and community, it is still under development. Here at Ericsson, the focus of our TinyML as-a-Service (TinyMLaaS) activity is to democratize TinyML, enabling manufacturers to start their AI businesses using TinyML, which runs on 32 bit microcontrollers. Our goal is to make the execution of ML tasks possible and easy in a specific class of devices. These devices are characterized by very constrained hardware and software resources such as sensor and actuator nodes based on these microcontrollers. The core componet of TinyMLaaS is Machine Learning Compiler (ML compiler)

References:

JH1: Instrumentation of Distributed Computing Systems

Tutor:  Jaakko Harjuhahto

PM: Bayesian preference learning and recommender systems

Tutor: Petrus Mikkola

The recent Bayesian machine learning techniques, which are build upon psychometrics and the economic utility theory, enable efficient preference learning and belief elicitation. The fundamental idea is to model the user’s latent valuation function (aka utility function) as a Gaussian process. From the application perspective, the research is closely related to recommender systems. The two main types of recommender systems are based on similarity computations over users (collaborative filtering) or over items (content-based filtering). The latter relates to the same problem that can be dealt with Bayesian preference learning. The goal of the thesis is to synthesize the research on recommender systems and Bayesian preference learning into a coherent literature review. Furthermore, it is possible to conduct an experimental comparison of reviewed methodologies.

References: 

• https://dl.acm.org/doi/10.1145/1102351.1102369 
• https://arxiv.org/abs/1704.03651 
• https://link.springer.com/chapter/10.1007/978-0-387-85820-3_1
  

RM1: Predict unplanned events with Twitter data

Tutor:  Rongjun Ma

Social media has been nowadays employed as a source of information for event detection. Better understanding these unplanned events in advance helps related departments to take timely actions, such as quick response to traffic congestions. Twitter, as a real-time social media, is widely researched for many use cases. Students will investigate these different use cases, try to summarize, and answer the research questions: What event attributes (geolocation, time, crowd size, etc.) can or can’t we get from Twitter, and how do we extract the information?

References:

• [1] Goh, G., Koh, J. Y., & Zhang, Y. (2018, November). Twitter-Informed Crowd Flow Prediction. In 2018 IEEE International Conference on Data Mining Workshops (ICDMW) (pp. 624-631). IEEE. http://kohjingyu.com/papers/Twitter_Informed_ICDM2018.pdf
  
•  [2] Ying, Y., Peng, C., Dong, C., Li, Y., & Feng, Y. (2018, August). Inferring event geolocation based on Twitter. In Proceedings of the 10th International Conference on Internet Multimedia Computing and Service (pp. 1-5). https://dl.acm.org/doi/pdf/10.1145/3240876.3240909?casa_token=v11zTBWLgGEAAAAA:HFeOfzYTMXvh6h36cKAdBSGdkvevFt2oQqWQJ1ATxRevNLbIMOePmkl-nW4ktmRgG819N5IR-h-F
•  [3] D'Andrea, E., Ducange, P., Lazzerini, B., & Marcelloni, F. (2015). Real-time detection of traffic from twitter stream analysis. IEEE transactions on intelligent transportation systems, 16(4), 2269-2283.
  

RM2: How do people make privacy decisions

Tutor:  Rongjun Ma

With the rapid growth of the internet, more and more individual information is exposed to the network. Inevitably, Privacy becomes a concern for everyone’s daily life as the disclosure of personal info might lead to financial or even physical attacks. What are the risks related to privacy issues that people are facing nowadays? And what are the factors people consider when making their privacy decisions? These are the research questions to be answered under this topic.

• [1] Adjerid, I., Peer, E., & Acquisti, A. (2016). Beyond the privacy paradox: Objective versus relative risk in privacy decision making. Available at SSRN 2765097. 
•  [2] Acquisti, A., & Grossklags, J. (2007). What can behavioral economics teach us about privacy. Digital privacy: theory, technologies and practices, 18, 363-377. https://www.heinz.cmu.edu/~acquisti/papers/Acquisti-Grossklags-Chapter-Etrics.pdf 
•  [3] Toch, E., Wang, Y., & Cranor, L. F. (2012). Personalization and privacy: a survey of privacy risks and remedies in personalization-based systems. User Modeling and User-Adapted Interaction, 22(1-2), 203-220.
  

SDP1: Tractable Deep Density Estimation with SPNs

Tutor: Sebastiaan De Peuter

Sum-product networks (SPNs) [1] are a class of deep probabilistic models for modeling joint densities. SPNs are tree-like computational structures containing sum nodes and product nodes where values flow from children to their parents. SPNs can be interpreted as latent variable models or as very large mixtures of factorization of the density they model. What makes SPNs interesting is that they allow you to tractably calculate any marginal and conditional of the joint density they model, which can be used to for example learn to complete images. Furthermore they naturally support a mixture of discrete and continuous variables. Parameters can be determined by gradient-based methods but learning the right structure for an SPN is still an area of active research (see [2] for a recent example). The goal for this project is for you to do a survey of the SPN literature, paying special attention to what novel applications SPNs have enabled. For the practically inclined this project can also involve a novel application or a comparison of SPN inference methods. The project will be carried out in the PML research group.

Tutor: Shaoxiong JI